{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:00:57Z","timestamp":1782856857969,"version":"3.54.5"},"reference-count":76,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002841","name":"Shanghai Educational Development Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002841","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Education Commission","doi-asserted-by":"publisher","award":["25CG258"],"award-info":[{"award-number":["25CG258"]}],"id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003024","name":"Shanghai Education Development Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62421004"],"award-info":[{"award-number":["62421004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116499","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:47:53Z","timestamp":1781884073000},"page":"116499","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TAPPS: Learning diverse policies via task-adaptive partial parameter sharing in heterogeneous multi-agent reinforcement learning"],"prefix":"10.1016","volume":"349","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5757-8674","authenticated-orcid":false,"given":"Mengke","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3728-0507","authenticated-orcid":false,"given":"Zijian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangfeng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116499_b1","doi-asserted-by":"crossref","unstructured":"H. Goel, Y. Zhang, M. Damani, G. Sartoretti, SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control, in: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023, pp. 1551\u20131559.","DOI":"10.65109\/GIFG9402"},{"key":"10.1016\/j.knosys.2026.116499_b2","article-title":"Coordlight: Learning decentralized coordination for network-wide traffic signal control","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b3","doi-asserted-by":"crossref","first-page":"24611","DOI":"10.52202\/068431-1787","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6623","key":"10.1016\/j.knosys.2026.116499_b4","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1126\/science.add4679","article-title":"Mastering the game of stratego with model-free multiagent reinforcement learning","volume":"378","author":"Perolat","year":"2022","journal-title":"Science"},{"key":"10.1016\/j.knosys.2026.116499_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113910","article-title":"A reinforcement learning and population-based discrete state transition algorithm for solving the multi-UAV task allocation problem with complex constraints","volume":"325","author":"Zhou","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"5","key":"10.1016\/j.knosys.2026.116499_b6","doi-asserted-by":"crossref","first-page":"3654","DOI":"10.1109\/TITS.2023.3336670","article-title":"A multi-agent reinforcement learning approach for safe and efficient behavior planning of connected autonomous vehicles","volume":"25","author":"Han","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"10.1016\/j.knosys.2026.116499_b7","doi-asserted-by":"crossref","first-page":"5374","DOI":"10.1109\/TITS.2023.3331723","article-title":"Multi-agent constrained policy optimization for conflict-free management of connected autonomous vehicles at unsignalized intersections","volume":"25","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"10","key":"10.1016\/j.knosys.2026.116499_b8","doi-asserted-by":"crossref","first-page":"4381","DOI":"10.1109\/TIV.2023.3296227","article-title":"Robust adversarial attacks detection based on explainable deep reinforcement learning for UAV guidance and planning","volume":"8","author":"Hickling","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.knosys.2026.116499_b9","doi-asserted-by":"crossref","unstructured":"P. Sunehag, G. Lever, A. Gruslys, W.M. Czarnecki, V. Zambaldi, M. Jaderberg, M. Lanctot, N. Sonnerat, J.Z. Leibo, K. Tuyls, et al., Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward, in: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, 2018, pp. 2085\u20132087.","DOI":"10.65109\/JSRC7365"},{"issue":"1","key":"10.1016\/j.knosys.2026.116499_b10","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116499_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127526","article-title":"Multi-agent reinforcement learning for cooperative search under aperiodically intermittent communication","volume":"280","author":"Fu","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"10.1016\/j.knosys.2026.116499_b12","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s10458-023-09633-6","article-title":"A survey of multi-agent deep reinforcement learning with communication","volume":"38","author":"Zhu","year":"2024","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"10.1016\/j.knosys.2026.116499_b13","doi-asserted-by":"crossref","unstructured":"L. Yang, P. Xu, S. Cao, Y. Ren, X. Chen, K. Huang, Uncertainty-Aware Opponent Modeling for Deep Reinforcement Learning, in: Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, 2025.","DOI":"10.65109\/SKPA8416"},{"key":"10.1016\/j.knosys.2026.116499_b14","series-title":"International Conference on Machine Learning","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","author":"Liu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116499_b15","series-title":"ICLR","article-title":"Maximum entropy heterogeneous-agent reinforcement learning","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116499_b16","unstructured":"J. Wang, Z. Ren, T. Liu, Y. Yu, C. Zhang, QPLEX: Duplex Dueling Multi-Agent Q-Learning, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.knosys.2026.116499_b17","first-page":"26516","article-title":"Multi agent reinforcement learning for sequential satellite assignment problems","volume":"vol. 39","author":"Holder","year":"2025"},{"key":"10.1016\/j.knosys.2026.116499_b18","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b19","first-page":"23049","article-title":"RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents","volume":"34","author":"Qiu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b20","unstructured":"T. Wang, T. Gupta, A. Mahajan, B. Peng, S. Whiteson, C. Zhang, RODE: Learning Roles to Decompose Multi-Agent Tasks, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.knosys.2026.116499_b21","unstructured":"T. Wang, H. Dong, V. Lesser, C. Zhang, ROMA: multi-agent reinforcement learning with emergent roles, in: Proceedings of the 37th International Conference on Machine Learning, 2020, pp. 9876\u20139886."},{"key":"10.1016\/j.knosys.2026.116499_b22","unstructured":"Z. Hu, Z. Zhang, H. Li, C. Chen, H. Ding, Z. Wang, Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.knosys.2026.116499_b23","doi-asserted-by":"crossref","first-page":"1698","DOI":"10.52202\/068431-0124","article-title":"Ldsa: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b24","doi-asserted-by":"crossref","first-page":"7155","DOI":"10.52202\/068431-0519","article-title":"Alma: Hierarchical learning for composite multi-agent tasks","volume":"35","author":"Iqbal","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b25","first-page":"11772","article-title":"Effective and stable role-based multi-agent collaboration by structural information principles","volume":"vol. 37","author":"Zeng","year":"2023"},{"issue":"32","key":"10.1016\/j.knosys.2026.116499_b26","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116499_b27","article-title":"Automatic grouping for efficient cooperative multi-agent reinforcement learning","volume":"36","author":"Zang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.knosys.2026.116499_b28","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/s10458-024-09665-6","article-title":"Team-wise effective communication in multi-agent reinforcement learning","volume":"38","author":"Yang","year":"2024","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"10.1016\/j.knosys.2026.116499_b29","series-title":"International Conference on Machine Learning","first-page":"4992","article-title":"The emergence of individuality","author":"Jiang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116499_b30","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI 2025, Montreal, Canada, August 16-22, 2025","first-page":"205","article-title":"Constructive conflict-driven multi-agent reinforcement learning for strategic diversity","author":"Mai","year":"2025"},{"key":"10.1016\/j.knosys.2026.116499_b31","doi-asserted-by":"crossref","first-page":"37011","DOI":"10.52202\/068431-2682","article-title":"Heterogeneous skill learning for multi-agent tasks","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b32","series-title":"Variational offline multi-agent skill discovery","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.116499_b33","first-page":"11595","article-title":"Contrastive identity-aware learning for multi-agent value decomposition","volume":"vol. 37","author":"Liu","year":"2023"},{"issue":"9","key":"10.1016\/j.knosys.2026.116499_b34","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1016\/j.tics.2013.06.004","article-title":"How neurons make meaning: brain mechanisms for embodied and abstract-symbolic semantics","volume":"17","author":"Pulverm\u00fcller","year":"2013","journal-title":"Trends Cogn. Sci."},{"issue":"2","key":"10.1016\/j.knosys.2026.116499_b35","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/s00426-023-01878-w","article-title":"Modal and amodal cognition: an overarching principle in various domains of psychology","volume":"88","author":"Kaup","year":"2024","journal-title":"Psychol. Res."},{"key":"10.1016\/j.knosys.2026.116499_b36","unstructured":"H. Qin, Z. Liu, C. Lin, C. Ma, S. Mei, S. Shen, C. Wang, GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning, in: Forty-Second International Conference on Machine Learning, 2025."},{"key":"10.1016\/j.knosys.2026.116499_b37","first-page":"1268","article-title":"Adaptively coordinating with novel partners via learned latent strategies","volume":"38","author":"Li","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b38","first-page":"11735","article-title":"Haven: Hierarchical cooperative multi-agent reinforcement learning with dual coordination mechanism","volume":"vol. 37","author":"Xu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116499_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106129","article-title":"Romat: Role-based multi-agent transformer for generalizable heterogeneous cooperation","volume":"174","author":"Wang","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2026.116499_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107093","article-title":"QTypeMix: Enhancing multi-agent cooperative strategies through heterogeneous and homogeneous value decomposition","volume":"184","author":"Fu","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2026.116499_b41","series-title":"International Conference on Machine Learning","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","author":"Christianos","year":"2021"},{"key":"10.1016\/j.knosys.2026.116499_b42","doi-asserted-by":"crossref","unstructured":"W. Kim, Y. Sung, Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning, in: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023, pp. 1942\u20131950.","DOI":"10.65109\/VUZV6508"},{"key":"10.1016\/j.knosys.2026.116499_b43","article-title":"ROTR: Role-transformable multi-agent resource allocation for nonstationary vehicular communications","author":"Li","year":"2025","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.knosys.2026.116499_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129535","article-title":"Dynamic subtask representation and assignment in cooperative multi-agent tasks","volume":"628","author":"You","year":"2025","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.knosys.2026.116499_b45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3779067","article-title":"ROIS: Role-based multi-agent collaboration by context-time-aware information sharing","volume":"17","author":"Qi","year":"2026","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.knosys.2026.116499_b46","first-page":"10707","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","volume":"33","author":"Christianos","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b47","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b48","doi-asserted-by":"crossref","unstructured":"S. Whiteson, M. Samvelyan, T. Rashid, C. De Witt, G. Farquhar, N. Nardelli, T. Rudner, C. Hung, P. Torr, J. Foerster, The StarCraft multi-agent challenge, in: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 2019, pp. 2186\u20132188.","DOI":"10.65109\/LVZZ5205"},{"key":"10.1016\/j.knosys.2026.116499_b49","doi-asserted-by":"crossref","first-page":"37567","DOI":"10.52202\/075280-1634","article-title":"Smacv2: An improved benchmark for cooperative multi-agent reinforcement learning","volume":"36","author":"Ellis","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b50","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"Foerster","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b51","series-title":"2023 IEEE\/CVF International Conference on Computer Vision","first-page":"9421","article-title":"Ndc-scene: Boost monocular 3d semantic scene completion in normalized device coordinates space","author":"Yao","year":"2023"},{"key":"10.1016\/j.knosys.2026.116499_b52","series-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","author":"Chu","year":"2017"},{"key":"10.1016\/j.knosys.2026.116499_b53","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume":"vol. 97","author":"Son","year":"2019"},{"key":"10.1016\/j.knosys.2026.116499_b54","doi-asserted-by":"crossref","unstructured":"B. Zhang, L. Li, Z. Xu, D. Li, G. Fan, Inducing stackelberg equilibrium through spatio-temporal sequential decision-making in multi-agent reinforcement learning, in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023, pp. 353\u2013361.","DOI":"10.24963\/ijcai.2023\/40"},{"key":"10.1016\/j.knosys.2026.116499_b55","doi-asserted-by":"crossref","unstructured":"D. Li, Z. Xu, B. Zhang, G. Zhou, Z. Zhang, G. Fan, From Explicit Communication to Tacit Cooperation: A Novel Paradigm for Cooperative MARL, in: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024, pp. 2360\u20132362.","DOI":"10.65109\/TAMH6534"},{"key":"10.1016\/j.knosys.2026.116499_b56","doi-asserted-by":"crossref","unstructured":"W. Kim, Y. Sung, Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning, in: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023, pp. 1942\u20131950.","DOI":"10.65109\/VUZV6508"},{"key":"10.1016\/j.knosys.2026.116499_b57","series-title":"International Conference on Machine Learning","first-page":"10041","article-title":"Maser: Multi-agent reinforcement learning with subgoals generated from experience replay buffer","author":"Jeon","year":"2022"},{"key":"10.1016\/j.knosys.2026.116499_b58","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"Mahajan","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b59","series-title":"International Conference on Machine Learning","first-page":"2778","article-title":"Curiosity-driven exploration by self-supervised prediction","author":"Pathak","year":"2017"},{"key":"10.1016\/j.knosys.2026.116499_b60","unstructured":"A.P. Badia, P. Sprechmann, A. Vitvitskyi, D. Guo, B. Piot, S. Kapturowski, O. Tieleman, M. Arjovsky, A. Pritzel, A. Bolt, et al., Never Give Up: Learning Directed Exploration Strategies, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.knosys.2026.116499_b61","unstructured":"B. Eysenbach, A. Gupta, J. Ibarz, S. Levine, Diversity is All You Need: Learning Skills without a Reward Function, in: International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.knosys.2026.116499_b62","series-title":"International Conference on Machine Learning","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","author":"Campos","year":"2020"},{"key":"10.1016\/j.knosys.2026.116499_b63","series-title":"Advances in Neural Information Processing Systems","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"Li","year":"2021"},{"key":"10.1016\/j.knosys.2026.116499_b64","unstructured":"L. Li, L. Yuan, P. Liu, T. Jiang, Y. Yu, LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination, in: Forty-Second International Conference on Machine Learning, 2025."},{"key":"10.1016\/j.knosys.2026.116499_b65","unstructured":"H. Goel, M. Omama, B. Chalaki, V. Tadiparthi, E.M. Pari, S.P. Chinchali, R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning, in: Forty-Second International Conference on Machine Learning."},{"key":"10.1016\/j.knosys.2026.116499_b66","unstructured":"Y. Yu, Q. Yin, J. Zhang, P. Xu, K. Huang, Admn: Agent-driven modular network for dynamic parameter sharing in cooperative multi-agent reinforcement learning, in: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, 2024, pp. 302\u2013310."},{"key":"10.1016\/j.knosys.2026.116499_b67","doi-asserted-by":"crossref","unstructured":"M. Tan, Multi-agent reinforcement learning: Independent vs. cooperative agents, in: Proceedings of the Tenth International Conference on Machine Learning, 1993, pp. 330\u2013337.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"10.1016\/j.knosys.2026.116499_b68","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/978-3-030-60990-0_12","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"Zhang","year":"2021","journal-title":"Handb. Reinf. Learn. Control."},{"key":"10.1016\/j.knosys.2026.116499_b69","doi-asserted-by":"crossref","unstructured":"M. Tan, Multi-agent reinforcement learning: Independent vs. cooperative agents, in: Proceedings of the Tenth International Conference on Machine Learning, 1993, pp. 330\u2013337.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"issue":"1","key":"10.1016\/j.knosys.2026.116499_b70","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0269888912000057","article-title":"Independent reinforcement learners in cooperative markov games: a survey regarding coordination problems","volume":"27","author":"Matignon","year":"2012","journal-title":"Knowl. Eng. Rev."},{"key":"10.1016\/j.knosys.2026.116499_b71","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6035","article-title":"Adaptive parameter sharing for multi-agent reinforcement learning","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116499_b72","series-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"Gutmann","year":"2010"},{"issue":"2","key":"10.1016\/j.knosys.2026.116499_b73","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1080\/10618600.1998.10474772","article-title":"Estimating mixture of Dirichlet process models","volume":"7","author":"MacEachern","year":"1998","journal-title":"J. Comput. Graph. Statist."},{"issue":"453","key":"10.1016\/j.knosys.2026.116499_b74","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1198\/016214501750332758","article-title":"Gibbs sampling methods for stick-breaking priors","volume":"96","author":"Ishwaran","year":"2001","journal-title":"J. Amer. Statist. Assoc."},{"key":"10.1016\/j.knosys.2026.116499_b75","article-title":"DIFFER: decomposing individual reward for fair experience replay in multi-agent reinforcement learning","volume":"36","author":"Hu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116499_b76","series-title":"Prioritized experience replay","author":"Schaul","year":"2015"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012256?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012256?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:55:23Z","timestamp":1782852923000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126012256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":76,"alternative-id":["S0950705126012256"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116499","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TAPPS: Learning diverse policies via task-adaptive partial parameter sharing in heterogeneous multi-agent reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116499","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116499"}}